© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41451
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of health and medical topics—illnesses, treatments, and medicine—often expressed in Portuguese/Spanish-style phrasing across languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çĹ
    -0.14
    çĹħ
    -0.12
    æĤ£èĢħ
    -0.12
     болез
    -0.11
     леÑĩ
    -0.11
     bá»ĩnh
    -0.11
     tails
    -0.10
     nemoc
    -0.10
     بÛĮÙħار
    -0.10
     illness
    -0.10
    POSITIVE LOGITS
     gall
    0.19
     Ast
    0.16
     Gall
    0.15
     heart
    0.15
     divert
    0.14
     sci
    0.14
     migr
    0.13
     bron
    0.13
     sugar
    0.13
    ecz
    0.12
    Activations Density 0.117%

    No Known Activations